© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12606
    Prev
    Next
    INDEX
    Explanations

    references to regulatory or legal frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.06
    2:0.07
    3:0.04
    4:0.03
    5:0.02
    6:0.04
    7:0.08
    8:0.07
    9:0.03
    10:0.41
    11:0.04
    Negative Logits
    ocl
    -3.24
    ��
    -2.91
     Muk
    -2.72
    atically
    -2.70
     Chand
    -2.69
    assium
    -2.64
    haps
    -2.61
     Bru
    -2.48
    MpServer
    -2.47
    SAY
    -2.46
    POSITIVE LOGITS
     e
    9.46
    e
    5.78
     eb
    5.15
     E
    4.39
     i
    4.38
     es
    4.04
     iT
    3.98
     eBook
    3.71
     eg
    3.71
    E
    3.67
    Activations Density 0.086%

    No Known Activations